用于对话中情感识别的上下文相关嵌入话语表示
Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversations
AI总结：
本文提出利用 RoBERTa 将历史对话轮次与目标话语共同编码，生成上下文相关话语嵌入，用于 ERC，并在 DailyDialog 和 EmoWOZ 上验证有效性。
摘要：
随着对话智能体变得越来越普遍，对话中的情感识别（Emotion Recognition in Conversations, ERC）正变得日益重要。识别情感是有效沟通的关键，也是开发有效且具有共情能力的对话智能体的关键组成部分。对对话上下文的了解和理解对于识别对话者的情感极具价值。因此，我们利用对话上下文来处理对话中的情感识别，即关注先前的对话轮次。建模对话上下文的通常方法是先生成每条话语的上下文无关表示，随后再对这些表示进行上下文建模。本文提出利用预训练 transformer 语言模型的上下文表示能力，为每条话语生成上下文相关的嵌入表示。在我们的方法中，将对话上下文附加到待分类话语之后，作为 RoBERTa 编码器的输入，并在该编码器后连接一个简单的分类模块；这样在获得嵌入后便无需再处理上下文，因为这些嵌入已经构成了对此类上下文的有效表示。我们还研究了引入的对话轮次数量如何影响模型性能。该方法的有效性在开放域 DailyDialog 数据集和面向任务的 EmoWOZ 数据集上得到了验证。
英文摘要：
Emotion Recognition in Conversations (ERC) has been gaining increasing importance as conversational agents become more and more common. Recognizing emotions is key for effective communication, being a crucial component in the development of effective and empathetic conversational agents. Knowledge and understanding of the conversational context are extremely valuable for identifying the emotions of the interlocutor. We thus approach Emotion Recognition in Conversations leveraging the conversational context, i.e., taking into attention previous conversational turns. The usual approach to model the conversational context has been to produce context-independent representations of each utterance and subsequently perform contextual modeling of these. Here we propose context-dependent embedding representations of each utterance by leveraging the contextual representational power of pre-trained transformer language models. In our approach, we feed the conversational context appended to the utterance to be classified as input to the RoBERTa encoder, to which we append a simple classification module, thus discarding the need to deal with context after obtaining the embeddings since these constitute already an efficient representation of such context. We also investigate how the number of introduced conversational turns influences our model performance. The effectiveness of our approach is validated on the open-domain DailyDialog dataset and on the task-oriented EmoWOZ dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
